Skip to main content

Linus Yifeng Tang

Linus Yifeng Tang

2024 Davidson Fellow
$10,000 Scholarship

Age: 18
Hometown: San Jose, CA

Mathematics: “Bounds on the Price of Feedback for Mistake-Bounded Online Learning

About Linus Yifeng

Hi! I’m Linus Tang, from San Jose, California. 

My hobbies include Go (a board game), card games, and writing math problems. I've also dabbled in physics, chess, and grid-based puzzle creation. I’m also a pianist, and I enjoy learning both classical music and piano covers of anime music. In the next few years, I plan to continue to develop skills in math and theoretical computer science research and solve real-world problems. 

Skip testimonial carousel

"I’m honored to be a Davidson Fellow! I’m lucky to have my work recognized in this way, and it has encouraged me to continue conducting math research."

Project Description

My project was on online learning, a form of machine learning in which a learner makes predictions based on a stream of data that appears over time. The learner receives feedback about its predictions that it uses to improve its model, allowing it to predict increasingly accurately. Online learning is often used for tasks like modeling the weather and recommending social media content. My mentor and I studied various scenarios in which an online learner is given weaker feedback. Our results provide effective methods to adapt standard-scenario algorithms to those that can learn under more difficult conditions, and quantify the difficulty of learning under various forms of feedback based on the worst-case number of incorrect predictions made by the learner.

Deeper Dive

I worked with my mentor, Dr. Jesse Geneson, researching the topic of mistake-bounded online learning, a form of machine learning in which the learner receives individual data points in real time, updating its model after each observation, rather than learning on the entire data set at once. Online learning is especially useful for making predictions that are affected by trends that change over time, such as weather and stock market predictions. Dr. Geneson and I studied and solved problems about the effects of weakened feedback in online learning—I was immediately captivated by the first problem Dr. Geneson showed me (an open problem studied and partially solved by a researcher named Philip Long) and was excited to begin researching. 

Often, I attempted a problem for hours without making tangible progress. The problems felt very daunting at times, due to the vast and elusive search space of strategies to consider. Whenever I felt like a certain approach to a problem was leaving me stuck, I took a step back and searched for new approaches and ideas. This experience taught me that in mathematical research, it pays to understand the surrounding literature very deeply. For instance, after reading Long’s method of making progress on the open problem just carefully enough to understand its steps, my first few attempts to solve the remaining case were clumsy and fruitless. Only after reading more thoroughly, going through the computations myself, and getting an intuitive grasp of the proof did I figure out how to modify Long’s strategy to tackle the final case. I owe huge thanks to my mentor Dr. Geneson, who met with me weekly to show me various possible directions to take our research, gave me feedback on my mathematical writing and advice about the research process, and supported me in so many other ways throughout the project. 

Since my work studies an idealized model of online learning, it’s difficult to apply the results directly to real-world machine learning. Still, they showcase some worst-case scenarios for learning under weakened feedback and present strategies that learn effectively even in these scenarios, which can be used to adapt online learning models to learn under more adverse conditions.

Q&A

What is one of your favorite quotes?

"Twenty years from now you will be more disappointed by the things you didn't do than by the things you did. So throw off the bowlines. Sail away from the safe harbor. Catch the trade winds in your sails. Explore. Dream. Discover" - Mark Twain (Samuel Clemens)

This quote is going to be especially relevant to me as I head off to college and take greater control of my life.

What is your favorite tradition or holiday?

My favorite family tradition is that whenever my family goes to the San Francisco Airport, we take a picture in front of the same colorful wall.

What is your favorite Olympic sport?

My favorite Olympic sport is table tennis, and I find it really exciting to watch. Although I don't have a table to play at home, I play table tennis whenever I go to a summer program that has a table.

Click image to download high resolution files

In The News

San Francisco – The Davidson Fellows Scholarship Program has announced the 2024 scholarship winners. Among the honorees are Samuel Yuan, 16, of Sunnyvale; Jingjing Liang, 16, of Cupertino; Michelle Wei, 18, of Saratoga; Vince Wu, 16, of Palo Alto; and Linus Tang, 18, of San Jose. Only 20 students across the country are recognized as 2024 scholarship winners.

Download the full press release here